Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,7 @@
import io.druid.indexing.common.actions.LockTryAcquireAction;
import io.druid.indexing.common.actions.SegmentTransactionalInsertAction;
import io.druid.indexing.common.actions.TaskActionClient;
import io.druid.indexing.firehose.IngestSegmentFirehoseFactory;
import io.druid.java.util.common.ISE;
import io.druid.java.util.common.granularity.Granularity;
import io.druid.java.util.common.guava.Comparators;
Expand Down Expand Up @@ -168,6 +169,12 @@ public TaskStatus run(final TaskToolbox toolbox) throws Exception
.isPresent();

final FirehoseFactory delegateFirehoseFactory = ingestionSchema.getIOConfig().getFirehoseFactory();

if (delegateFirehoseFactory instanceof IngestSegmentFirehoseFactory) {
// pass toolbox to Firehose
((IngestSegmentFirehoseFactory) delegateFirehoseFactory).setTaskToolbox(toolbox);
}

final FirehoseFactory firehoseFactory;
if (ingestionSchema.getIOConfig().isSkipFirehoseCaching()
|| delegateFirehoseFactory instanceof ReplayableFirehoseFactory) {
Expand Down Expand Up @@ -290,7 +297,10 @@ private Map<Interval, List<ShardSpec>> determineShardSpecs(
hllCollectors.put(interval, Optional.of(HyperLogLogCollector.makeLatestCollector()));
}

List<Object> groupKey = Rows.toGroupKey(queryGranularity.bucketStart(inputRow.getTimestamp()).getMillis(), inputRow);
List<Object> groupKey = Rows.toGroupKey(
queryGranularity.bucketStart(inputRow.getTimestamp()).getMillis(),
inputRow
);
hllCollectors.get(interval).get().add(hashFunction.hashBytes(jsonMapper.writeValueAsBytes(groupKey)).asBytes());
}
}
Expand Down Expand Up @@ -385,7 +395,12 @@ public SegmentIdentifier allocate(DateTime timestamp, String sequenceName, Strin

try (
final Appenderator appenderator = newAppenderator(fireDepartmentMetrics, toolbox, dataSchema);
final FiniteAppenderatorDriver driver = newDriver(appenderator, toolbox, segmentAllocator, fireDepartmentMetrics);
final FiniteAppenderatorDriver driver = newDriver(
appenderator,
toolbox,
segmentAllocator,
fireDepartmentMetrics
);
final Firehose firehose = firehoseFactory.connect(dataSchema.getParser())
) {
final Supplier<Committer> committerSupplier = Committers.supplierFromFirehose(firehose);
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,7 @@ public class IngestSegmentFirehoseFactory implements FirehoseFactory<InputRowPar
private final List<String> metrics;
private final Injector injector;
private final IndexIO indexIO;
private TaskToolbox taskToolbox;

@JsonCreator
public IngestSegmentFirehoseFactory(
Expand Down Expand Up @@ -121,21 +122,28 @@ public List<String> getMetrics()
return metrics;
}

public void setTaskToolbox(TaskToolbox taskToolbox)
{
this.taskToolbox = taskToolbox;
}

@Override
public Firehose connect(InputRowParser inputRowParser) throws IOException, ParseException
{
log.info("Connecting firehose: dataSource[%s], interval[%s]", dataSource, interval);
// better way to achieve this is to pass toolbox to Firehose, The instance is initialized Lazily on connect method.
// Noop Task is just used to create the toolbox and list segments.
final TaskToolbox toolbox = injector.getInstance(TaskToolboxFactory.class).build(
new NoopTask("reingest", 0, 0, null, null, null)
);

if (taskToolbox == null) {
// Noop Task is just used to create the toolbox and list segments.
taskToolbox = injector.getInstance(TaskToolboxFactory.class).build(
new NoopTask("reingest", 0, 0, null, null, null)
);
}

try {
final List<DataSegment> usedSegments = toolbox
final List<DataSegment> usedSegments = taskToolbox
.getTaskActionClient()
.submit(new SegmentListUsedAction(dataSource, interval, null));
final Map<DataSegment, File> segmentFileMap = toolbox.fetchSegments(usedSegments);
final Map<DataSegment, File> segmentFileMap = taskToolbox.fetchSegments(usedSegments);
VersionedIntervalTimeline<String, DataSegment> timeline = new VersionedIntervalTimeline<>(
Ordering.<String>natural().nullsFirst()
);
Expand Down